graphql-architect
Fail
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a documentation link (https://jeffallan.github.io/claude-skills/skills/api-architecture/graphql-architect/) that has been blacklisted by automated reputation scanners (URL:Blacklist). This link is presented as the primary documentation source for the skill.- [METADATA_POISONING]: The skill's primary instruction file (SKILL.md) was flagged by reputation scanners as containing potential malware indicators (FileRepMalware). This detection is a significant concern as it involves the core instruction set for the agent.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon user-provided domain models and requirements to design GraphQL architectures, creating a surface for indirect prompt injection attacks.
- Ingestion points: Business requirements and domain descriptions provided by the user in conversation.
- Boundary markers: None identified; the instructions lack delimiters or warnings to ignore embedded instructions in user-provided data.
- Capability inventory: The skill provides instructions for generating complex resolver code, security rules, and database interaction patterns.
- Sanitization: No validation or sanitization steps are defined for processing external domain models.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata